© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 18606
    Prev
    Next
    INDEX
    Explanations

    phrases related to asserting opinions or beliefs

    oai_token-act-pair · gpt-3.5-turbo

    actions related to coercion or mandatory requirements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Dim
    -0.70
    ,—
    -0.65
    dim
    -0.63
    see
    -0.61
    RET
    -0.60
    burning
    -0.60
    ersen
    -0.60
    uyomi
    -0.59
    Interested
    -0.58
    .........
    -0.56
    POSITIVE LOGITS
     oneself
    0.81
     entails
    0.76
     yourself
    0.67
     involves
    0.67
     isn
    0.66
    ealous
    0.66
     helps
    0.65
     doesn
    0.64
     someone
    0.64
     truthful
    0.61
    Activations Density 0.299%

    No Known Activations